Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Wheel scratch detection method based on improved mapping fusion features and threshold values

A technology that combines features and wheel scratches, which is applied in railway vehicle testing, voice analysis, instruments, etc., can solve the problems of slow speed and low precision of scratch signals, and achieve the goals of saving running time, reducing feature dimensions, and high detection accuracy Effect

Pending Publication Date: 2021-12-31
HARBIN INST OF TECH +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problems of slow speed and low precision of existing scratch signal detection methods, the present invention provides a wheel scratch detection method based on improved mapping fusion features and thresholds

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Wheel scratch detection method based on improved mapping fusion features and threshold values
  • Wheel scratch detection method based on improved mapping fusion features and threshold values
  • Wheel scratch detection method based on improved mapping fusion features and threshold values

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The technical solution of the present invention will be further described below in conjunction with the accompanying drawings, but it is not limited thereto. Any modification or equivalent replacement of the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention should be covered by the present invention. within the scope of protection.

[0024] The present invention provides a wheel scratch detection method based on improved mapping fusion features and thresholds. First, the feature set is designed to be extracted from the acquired acoustic emission signal, including root mean square value, entropy, kurtosis spectrum, skewness spectrum, Mel spectrum cepstral coefficient, gamma spectrum cepstral coefficient and third-order wavelet energy entropy, a total of seven features; then three screening factors of scratch signal detection rate, precision rate and the comprehensive coefficient of th...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a wheel scratch detection method based on improved mapping fusion features and threshold values, and the method comprises the following steps: 1, loading P groups of wheel acoustic emission signals, extracting seven features from each group of signals, determining the extreme value of each group of features, and calculating the average value of the extreme values of the P groups of features; 2, taking the obtained average value as a detection threshold value, performing preliminary detection on the acoustic emission signals, calculating a scratch signal detection rate and a precision rate of each feature, performing feature screening on multi-dimensional features to obtain a low-dimensional feature parameter set, and performing mapping fusion on the low-dimensional feature parameter set to obtain a one-dimensional fusion feature; and 3, calculating a standard deviation, a mean value and a minimum value of the mapping fusion features, calculating an improved adaptive detection threshold in each time window, judging whether each feature belongs to a scratch signal or not according to an improved adaptive threshold judgment algorithm, and completing wheel scratch acoustic emission signal detection. According to the invention, the wheel scratch signal detection rate and detection precision can be greatly improved, and the safe operation guarantee requirement of a train is met.

Description

technical field [0001] The invention relates to a wheel scratch signal processing and detection method, in particular to a wheel scratch detection method based on improved mapping fusion features and thresholds. Background technique [0002] The railway is an important transportation facility of the country and the main artery of the country's economic development, which is closely related to the production and life of the people. In the 1860s, China’s first railway, the Wusong Railway, appeared. So far, China’s railways have a history of more than 160 years. Since the beginning of the 21st century, with the rapid development of material science and manufacturing technology, China’s railway industry has developed by leaps and bounds. It is expected that By the end of 2021, the total mileage of China's railway operations will exceed 146,000 kilometers, ranking first in the world. China's "eight vertical and eight horizontal" railways are deployed all over the country, coveri...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G10L25/51G10L25/03G10L25/24G10L25/18G01M17/10
CPCG10L25/51G10L25/03G10L25/24G10L25/18G01M17/10
Inventor 沈毅常永祺章欣黄俐王艳刘金明郭晓棠张军王军李博
Owner HARBIN INST OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products